Abstract: Abnormal values of an objective variable are removed. A degree of association between an objective variable and a plurality of explanatory variables is calculated. A plurality of explanatory variables having a high degree of association are extracted. A degree of independence between the explanatory variables is calculated. A plurality of candidates of explanatory variables with a high possibility of having a great effect on the objective variable are selected based on the degree of association and the degree of independence. An explanatory variable having a high rate of contribution to the objective variable is selected from among the candidates, based on the cumulative contribution rate, and a regression equation is calculated to estimate a value of the objective variable. The same processing is repeated, using the difference as a new objective variable and explanatory variables except the explanatory variable used to obtain the difference as new explanatory variables.

Abstract: It is an object of the present invention to improve analysis accuracy of manufacture data with missing values. First, an analysis target explanatory variable is selected. The manufacture data acquired from each process is separated into a set with missing values and a set without missing values. An evaluation value for evaluating the influence of the explanatory variable on the objective variable is calculated from the manufacture data in the set with missing value and the set without missing values. The manufacture data is analyzed by matching the calculated evaluation value with a reference.

Abstract: Abnormal values of an objective variable are removed. A degree of association between an objective variable and a plurality of explanatory variables is calculated. A plurality of explanatory variables having a high degree of association are extracted. A degree of independence between the explanatory variables is calculated. A plurality of candidates of explanatory variables with a high possibility of having a great effect on the objective variable are selected based on the degree of association and the degree of independence. An explanatory variable having a high rate of contribution to the objective variable is selected from among the candidates, based on the cumulative contribution rate, and a regression equation is calculated to estimate a value of the objective variable. The same processing is repeated, using the difference as a new objective variable and explanatory variables except the explanatory variable used to obtain the difference as new explanatory variables.

Abstract: It is an object of the present invention to improve analysis accuracy of manufacture data with missing values. First, an analysis target explanatory variable is selected. The manufacture data acquired from each process is separated into a set with missing values and a set without missing values. An evaluation value for evaluating the influence of the explanatory variable on the objective variable is calculated from the manufacture data in the set with missing value and the set without missing values. The manufacture data is analyzed by matching the calculated evaluation value with a reference.

Abstract: A data analysis method allows a correlation between variables to be efficiently extracted from a record group. A record group sort unit of a computer sorts the target record group by the magnitude of a specified variable, for instance. A record group divide-and-extract unit divides the sorted target record group in a specified dividing manner (four-part division or eight-part division, for instance) and extracts subordinate record groups. A correlation calculation unit calculates a correlation between specified variables in each of the subordinate record groups.

Abstract: Data to be analyzed, for example, a yield value and various measurement values are selected and extracted from an original data group (step S1). At least one data distribution characteristic is extracted with respect to the extracted data (step S2). The data distribution characteristic amount to be analyzed is selected from these characteristics, and data mining such as a regression tree analysis is performed, designating it as a target variable (step S3). After the regression tree analysis has been completed with respect to all the extracted data distribution characteristics (step S4), the analysis result is output, and the engineer confirms it (step S5), and makes a decision (step S6).

Abstract: A rule present between a plurality of data values is extracted through data mining to output the rule and the information showing the reliability of the rule. A set-division evaluation-value S-ratio and a t-value showing the clearness of division when dividing a set constituted of a plurality of data values into two subsets are defined as the information showing the reliability of a rule. S-ratio=((S1+S2)/2)/S0 wherein, S0 is sum of squares of purpose variables of set before divided, S1, S2 are sums of squares of purpose variables of each subset after divided.

Abstract: Data to be analyzed, for example, a yield value and various measurement values are selected and extracted from an original data group (step S1). At least one data distribution characteristic is extracted with respect to the extracted data (step S2). The data distribution characteristic amount to be analyzed is selected from these characteristics, and data mining such as a regression tree analysis is performed, designating it as a target variable (step S3). After the regression tree analysis has been completed with respect to all the extracted data distribution characteristics (step S4) the analysis result is output, and the engineer confirms it (step S5), and makes a decision (step S6).

Abstract: A rule present between a plurality of data values is extracted through data mining to output the rule and the information showing the reliability of the rule. A set-division evaluation-value S-ratio and a t-value showing the clearness of division when dividing a set constituted of a plurality of data values into two subsets are defined as the information showing the reliability of a rule.